Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5011
    Prev
    Next
    INDEX
    Explanations

    generic punctuation or formatting symbols often used in textual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.70
    Sklici
    -0.68
    Autoritní
    -0.63
     estekak
    -0.63
     ligiloj
    -0.63
    GEBURTSDATUM
    -0.61
    [])
    
    -0.61
    انجليز
    -0.60
    %;
    
    -0.59
    #
    -0.58
    POSITIVE LOGITS
    Anyway
    0.85
     Anyway
    0.85
     Anyways
    0.77
    Anyways
    0.74
     digress
    0.70
     Sorry
    0.70
     sorry
    0.67
    Bref
    0.66
    Sorry
    0.63
    Anyhow
    0.61
    Activations Density 0.293%

    No Known Activations